End of training

README.md

@@ -1,14 +1,14 @@
 ---
 library_name: peft
 license: apache-2.0
-base_model: 01-ai/Yi-1.5-9B-Chat-16K
+base_model: unsloth/mistral-7b-instruct-v0.2
 tags:
 - axolotl
 - generated_from_trainer
 datasets:
-- Aivesa/dataset_042b5f5f-32d6-47b9-b2e4-5373647ef8f2
+- Aivesa/dataset_cb3acbb3-babd-4857-af0b-0acdfd981c3f
 model-index:
-- name: 32546f09-c053-4243-8a22-3c00ead461eb
+- name: 6272701b-9847-425c-8ff7-08f7e2fe06c3
   results: []
 ---
 
@@ -21,18 +21,18 @@ should probably proofread and complete it, then remove this comment. -->
 axolotl version: `0.6.0`
 ```yaml
 adapter: lora
-base_model: 01-ai/Yi-1.5-9B-Chat-16K
+base_model: unsloth/mistral-7b-instruct-v0.2
 bf16: auto
 chat_template: llama3
 dataset_prepared_path: /workspace/axolotl/data/prepared
 datasets:
 - ds_type: json
   format: custom
-  path: Aivesa/dataset_042b5f5f-32d6-47b9-b2e4-5373647ef8f2
+  path: Aivesa/dataset_cb3acbb3-babd-4857-af0b-0acdfd981c3f
   type:
-    field_input: my_solu
-    field_instruction: prompt
-    field_output: solution
+    field_input: yl
+    field_instruction: x
+    field_output: yw
     system_format: '{system}'
     system_prompt: ''
 debug: null
@@ -48,7 +48,7 @@ fsdp_config: null
 gradient_accumulation_steps: 4
 gradient_checkpointing: false
 group_by_length: false
-hub_model_id: Aivesa/32546f09-c053-4243-8a22-3c00ead461eb
+hub_model_id: Aivesa/6272701b-9847-425c-8ff7-08f7e2fe06c3
 hub_private_repo: true
 hub_repo: null
 hub_strategy: checkpoint
@@ -88,10 +88,10 @@ use_accelerate: true
 val_set_size: 0.05
 wandb_entity: null
 wandb_mode: online
-wandb_name: 042b5f5f-32d6-47b9-b2e4-5373647ef8f2
+wandb_name: cb3acbb3-babd-4857-af0b-0acdfd981c3f
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
-wandb_runid: 042b5f5f-32d6-47b9-b2e4-5373647ef8f2
+wandb_runid: cb3acbb3-babd-4857-af0b-0acdfd981c3f
 warmup_steps: 10
 weight_decay: 0.0
 xformers_attention: null
@@ -100,11 +100,11 @@ xformers_attention: null
 
 </details><br>
 
-# 32546f09-c053-4243-8a22-3c00ead461eb
+# 6272701b-9847-425c-8ff7-08f7e2fe06c3
 
-This model is a fine-tuned version of [01-ai/Yi-1.5-9B-Chat-16K](https://huggingface.co/01-ai/Yi-1.5-9B-Chat-16K) on the Aivesa/dataset_042b5f5f-32d6-47b9-b2e4-5373647ef8f2 dataset.
+This model is a fine-tuned version of [unsloth/mistral-7b-instruct-v0.2](https://huggingface.co/unsloth/mistral-7b-instruct-v0.2) on the Aivesa/dataset_cb3acbb3-babd-4857-af0b-0acdfd981c3f dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.8782
+- Loss: 1.0659
 
 ## Model description
 
@@ -138,9 +138,9 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| 1.0157        | 0.0017 | 3    | 1.0931          |
-| 1.2851        | 0.0034 | 6    | 1.0198          |
-| 0.9428        | 0.0051 | 9    | 0.8782          |
+| 5.3218        | 0.0001 | 3    | 1.3255          |
+| 5.0832        | 0.0002 | 6    | 1.1658          |
+| 3.9279        | 0.0003 | 9    | 1.0659          |
 
 
 ### Framework versions